Meta-Reinforcement Learning via Language Instructions.
Zhenshan BingAlexander W. KochXiangtong YaoKai HuangAlois KnollPublished in: ICRA (2023)
Keyphrases
- reinforcement learning
- programming language
- meta level
- computer programs
- model free
- function approximation
- natural language
- language learning
- reinforcement learning algorithms
- modeling language
- learning problems
- state space
- learning process
- multi agent
- data mining
- robotic control
- transition model
- language processing
- context dependent
- optimal control
- optimal policy
- supervised learning
- knowledge base